Ultra-Wideband Indoor Positioning and IMU-Based Activity Recognition for Ice Hockey Analytics

Currently, gathering statistics and information for ice hockey training purposes mostly happens by hand, whereas the automated systems that do exist are expensive and difficult to set up. To remedy this, in this paper, we propose and analyse a wearable system that combines player localisation and activity classification to automatically gather information. A stick-worn inertial measurement unit was used to capture acceleration and rotation data from six ice hockey activities. A convolutional neural network was able to distinguish the six activities from an unseen player with a 76% accuracy at a sample frequency of 100 Hz. Using unseen data from players used to train the model, a 99% accuracy was reached. With a peak detection algorithm, activities could be automatically detected and extracted from a complete measurement for classification. Additionally, the feasibility of a time difference of arrival based ultra-wideband system operating at a 25 Hz update rate was determined. We concluded that the system, when the data were filtered and smoothed, provided acceptable accuracy for use in ice hockey. Combining both, it was possible to gather useful information about a wide range of interesting performance measures. This shows that our proposed system is a suitable solution for the analysis of ice hockey.

[1]  Sam Lemey,et al.  Wi-PoS: A Low-Cost, Open Source Ultra-Wideband (UWB) Hardware Platform with Long Range Sub-GHz Backbone , 2019, Sensors.

[2]  Karl Schulte,et al.  Dielectric properties of epoxy/short carbon fiber composites , 2010 .

[3]  Julius Hannink,et al.  Activity recognition in beach volleyball using a Deep Convolutional Neural Network , 2017, Data Mining and Knowledge Discovery.

[4]  Sunil Kumar,et al.  Efficient characterization of tennis shots and game analysis using wearable sensors data , 2015, 2015 IEEE SENSORS.

[5]  Yang Xue,et al.  Sport-Related Human Activity Detection and Recognition Using a Smartwatch , 2019, Sensors.

[6]  Matteo Ridolfi,et al.  Experimental Evaluation of UWB Indoor Positioning for Sport Postures , 2018, Sensors.

[7]  Marko Malajner,et al.  UWB ranging accuracy , 2015, 2015 International Conference on Systems, Signals and Image Processing (IWSSIP).

[8]  Wes McKinney,et al.  pandas: a Foundational Python Library for Data Analysis and Statistics , 2011 .

[9]  Akseli Aalto,et al.  Scouting technical skills in ice hockey , 2012 .

[10]  Bertrand Perrat,et al.  Quality assessment of an Ultra-Wide Band positioning system for indoor wheelchair court sports , 2015 .

[11]  Jürgen Freiwald,et al.  Validity and reliability of GPS and LPS for measuring distances covered and sprint mechanical properties in team sports , 2018, PloS one.

[12]  Fernando Seco Granja,et al.  Comparing Ubisense, BeSpoon, and DecaWave UWB Location Systems: Indoor Performance Analysis , 2017, IEEE Transactions on Instrumentation and Measurement.

[13]  Giuseppe Rabita,et al.  Validity of an ultra-wideband local positioning system to assess specific movements in handball , 2020, Biology of sport.

[14]  Thad B. Welch,et al.  The effects of the human body on UWB signal propagation in an indoor environment , 2002, IEEE J. Sel. Areas Commun..

[15]  Hend Suliman Al-Khalifa,et al.  Ultra Wideband Indoor Positioning Technologies: Analysis and Recent Advances † , 2016, Sensors.

[16]  Björn Eskofier,et al.  Sensor-based stroke detection and stroke type classification in table tennis , 2015, SEMWEB.

[17]  Anton Umek,et al.  Application for Impact Position Evaluation in Tennis Using UWB Localization , 2018, IIKI.

[18]  Matthias Gilgien,et al.  Validity of the Catapult ClearSky T6 Local Positioning System for Team Sports Specific Drills, in Indoor Conditions , 2018, Front. Physiol..

[19]  M. S. Sarto,et al.  Effective Properties of Carbon Fiber Composites: EM Modeling Versus Experimental Testing , 2007, 2007 IEEE International Symposium on Electromagnetic Compatibility.

[20]  A. Yarovoy,et al.  Human Body Impact on UWB Antenna Radiation , 2012 .

[21]  John F. Alexander,et al.  Comparison of the Ice Hockey Wrist and Slap Shots for Speed and Accuracy , 1963 .

[22]  Kevin I-Kai Wang,et al.  Human Body Shadowing Effect on UWB-Based Ranging System for Pedestrian Tracking , 2019, IEEE Transactions on Instrumentation and Measurement.

[23]  V. Dubey,et al.  MEMS Technology: A Review , 2019, Journal of Engineering Research and Reports.

[24]  Toon De Pessemier,et al.  Badminton Activity Recognition Using Accelerometer Data , 2020, Sensors.

[25]  Adam S Douglas,et al.  Tracking In-Match Movement Demands Using Local Positioning System in World-Class Men's Ice Hockey. , 2019, Journal of strength and conditioning research.

[26]  D. Pearsall,et al.  Design and Materials in Ice Hockey , 2019, Materials in Sports Equipment.

[27]  Michael Lawo,et al.  Recognizing Physical Training Exercises Using the Axivity Device , 2013 .

[28]  Xiaopeng Sha,et al.  Basketball Movements Recognition Using a Wrist Wearable Inertial Measurement Unit , 2018, 2018 IEEE 1st International Conference on Micro/Nano Sensors for AI, Healthcare, and Robotics (NSENS).

[29]  Kin K. Leung,et al.  A Survey of Indoor Localization Systems and Technologies , 2017, IEEE Communications Surveys & Tutorials.

[30]  K. Shadan,et al.  Available online: , 2012 .

[31]  Gerhard Tröster,et al.  Sensor technology for ice hockey and skating , 2015, 2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN).

[32]  Peio Lopez-Iturri,et al.  Effects of the Body Wearable Sensor Position on the UWB Localization Accuracy , 2019 .

[33]  Tareq Abed Mohammed,et al.  Understanding of a convolutional neural network , 2017, 2017 International Conference on Engineering and Technology (ICET).

[34]  W G Hopkins,et al.  Validity of an ultra-wideband local positioning system to measure locomotion in indoor sports , 2018, Journal of sports sciences.

[35]  Qining Wang,et al.  IMU-based underwater sensing system for swimming stroke classification and motion analysis , 2017, 2017 IEEE International Conference on Cyborg and Bionic Systems (CBS).

[36]  Ho Chul Kim,et al.  Electrical properties of unidirectional carbon-epoxy composites in wide frequency band , 1990 .

[37]  Kaveh Pahlavan,et al.  Toward Accurate Human Tracking: Modeling Time-of-Arrival for Wireless Wearable Sensors in Multipath Environment , 2014, IEEE Sensors Journal.

[38]  Nishant Doshi,et al.  Human Activity Recognition: A Survey , 2019, Procedia Computer Science.

[39]  Gui-Bin Bian,et al.  Performance Analysis of Google Colaboratory as a Tool for Accelerating Deep Learning Applications , 2018, IEEE Access.

[40]  Etsuo Chosa,et al.  Identification of key events in baseball hitting using inertial measurement units. , 2019, Journal of biomechanics.

[41]  Akash Anand,et al.  Wearable Motion Sensor Based Analysis of Swing Sports , 2017, 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA).

[42]  Akram Alomainy,et al.  Experimental Investigation of 3-D Human Body Localization Using Wearable Ultra-Wideband Antennas , 2015, IEEE Transactions on Antennas and Propagation.